I'm Nobuhiro Ueda.

I am a researcher at the Data Science Laboratory, NEC Corporation. I am working on R&D of large language models and natural language processing.


Nobuhiro Ueda Profile Pic

About Me

I am a researcher at the Data Science Laboratory, NEC Corporation, Japan. I'm interested in how we can make computers understand natural language. Previously, I was working on a research about anaphora resolution in Japanese. Try our Japanese anaphora resolution demo.

Contact Details

Nobuhiro Ueda
NEC Tamagawa Office, NEC Corporation
Nakahara-ku Shimonumabe 1753, Kawasaki, Kanagawa, 211-0011, Japan

ueda at nlp.ist.i.kyoto-u.ac.jp

Education

Graduate School of Informatics, Kyoto University

Ph.D. of Informatics April 2021 - March 2024

Worked on research about natural language processing.

Graduate School of Informatics, Kyoto University

Master of Informatics April 2019 - March 2021

Worked on research about natural language processing.

Faculty of Engineering, Kyoto University

Bachelor of Engineering April 2015 - March 2019

Learned about a wide range of engineering topics, including calculus, linear algebra, statistics, electronics, electromagnetism, and computer science.

Publications

International Conferences and Workshops (Peer-reviewed)

  • J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution

    Nobuhiro Ueda, Hideko Habe, Yoko Matsui, Akishige Yuguchi, Seiya Kawano, Yasutomo Kawanishi, Sadao Kurohashi and Koichiro Yoshino
    Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Turin, Italy, (2024.5).
    [paper][dataset][code]

  • Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese

    Yikun Sun, Zhen Wan, Nobuhiro Ueda, Sakiko Yahata, Fei Cheng, Chenhui Chu and Sadao Kurohashi
    Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Turin, Italy, (2024.5).
    [paper][dataset][code]

  • KWJA: A Unified Japanese Analyzer Based on Foundation Models

    Nobuhiro Ueda, Kazumasa Omura, Takashi Kodama, Hirokazu Kiyomaru, Yugo Murawaki, Daisuke Kawahara and Sadao Kurohashi
    Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023): System Demonstrations, Toronto, Canada, (2023.7).
    [paper][code][demo][poster]

  • Improving Bridging Reference Resolution using Continuous Essentiality from Crowdsourcing

    Nobuhiro Ueda and Sadao Kurohashi
    Proceedings of the Fifth Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC 2022), Gyeongju, Republic of Korea, (2022.10).
    [paper][code1][code2][slides]

  • BERT-based Cohesion Analysis of Japanese Texts

    Nobuhiro Ueda, Daisuke Kawahara and Sadao Kurohashi
    Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), Online, (2020.12).
    [paper][code][errata]

  • A System for Worldwide COVID-19 Information Aggregation

    Akiko Aizawa, Frederic Bergeron, Junjie Chen, Fei Cheng, Katsuhiko Hayashi, Kentaro Inui, Hiroyoshi Ito, Daisuke Kawahara, Masaru Kitsuregawa, Hirokazu Kiyomaru, Masaki Kobayashi, Takashi Kodama, Sadao Kurohashi, Qianying Liu, Masaki Matsubara, Yusuke Miyao, Atsuyuki Morishima, Yugo Murawaki, Kazumasa Omura, Haiyue Song, Eiichiro Sumita, Shinji Suzuki, Ribeka Tanaka, Yu Tanaka, Masashi Toyoda, Nobuhiro Ueda, Honai Ueoka, Masao Utiyama, Ying Zhong
    Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020, Online, (2020.12).
    [paper][url]

Domestic Conferences

  • 実世界対話におけるフレーズグラウンディングモデルの評価と分析

    植田 暢大, 波部 英子, 松井 陽子, 湯口 彰重, 河野 誠也, 川西 康友, 黒橋 禎夫, 吉野 幸一郎
    言語処理学会 第30回年次大会, 神戸, (2024.3).
    [paper][slides]

  • llm-jp-eval: 日本語大規模言語モデルの自動評価ツール

    Namgi Han, 植田 暢大, 大嶽 匡俊, 勝又 智, 鎌田 啓輔, 清丸 寛一, 児玉 貴志, 菅原 朔, Bowen Chen, 松田 寛, 宮尾 祐介, 村脇 有吾, 劉 弘毅
    言語処理学会 第30回年次大会, 神戸, (2024.3).
    [paper][slides]

  • 実世界における総合的参照解析を目的としたマルチモーダル対話データセットの構築

    植田 暢大, 波部 英子, 湯口 彰重, 河野 誠也, 川西 康友, 黒橋 禎夫, 吉野 幸一郎
    言語処理学会 第29回年次大会, 沖縄, (2023.3).
    [paper][slides]Award Icon委員特別賞

  • テキスト生成モデルによる日本語形態素解析

    児玉 貴志, 植田 暢大, 大村 和正, 清丸 寛一, 村脇 有吾, 河原 大輔, 黒橋 禎夫
    言語処理学会 第29回年次大会, 沖縄, (2023.3).
    [paper][code]

  • KWJA:汎用言語モデルに基づく日本語解析器

    植田 暢大, 大村 和正, 児玉 貴志, 清丸 寛一, 村脇 有吾, 河原 大輔 and 黒橋 禎夫
    情報処理学会 第253回自然言語処理研究会, 京都, (2022.9).
    [paper][code][slides]Award Icon優秀研究賞

  • BERTとRefinementネットワークによる統合的照応・共参照解析

    植田 暢大, 河原 大輔, 黒橋 禎夫
    言語処理学会 第26回年次大会, 茨城, (2020.3).
    [paper]Award Icon若手奨励賞

  • 因果関係グラフ: 構造的言語処理に基づくイベントの原因・結果・解決策の集約

    清丸 寛一, 植田 暢大, 児玉 貴志, 田中 佑, 岸本 裕大, 田中 リベカ, 河原 大輔, 黒橋 禎夫
    言語処理学会 第26回年次大会, 茨城, (2020.3).
    [paper]

Experience

researcher

  • NEC Corporation

    Kawasaki, KanagawaApril 2024 - Present
    [website]

hackathon

  • 16th Young Researcher Association for NLP Studies (YANS) Symposium Hackathon

    OnlineAugust 2021
    [report][code]Award Icon2nd place

teaching assistant

  • 「人を知る」人工知能講座2022

    OnlineNovember 2022
    [website]

  • 「人を知る」人工知能講座2021

    OnlineNovember 2021
    [website]

  • C Programming Class (2021)

    Kyoto University, KyotoApril 2021 - July 2021

  • 「人を知る」人工知能講座2020

    OnlineNovember 2020
    [website]

  • 「人を知る」人工知能講座2019

    Shin-marunouchi Building, TokyoNovember 2019
    [website]

  • C Programming Class (2019)

    Kyoto University, KyotoApril 2019 - July 2019

internship

  • M3, Inc.

    Akasaka Intercity, TokyoSeptember 2019
    Worked on improving recommendation system for medical articles.

  • LINE

    LINE KYOTO, KyotoAugust 2019
    Joined a hackathon to develop an application like Akinator, which runs on LINE.
    [report]

presentation & talks

  • 日本語DeBERTaモデルの構築 (JLR2023)

    Okinawa Convention Center, OkinawaMarch 2023
    Gave a lightning talk on Japanese foundation models I developed.
    [website][slides]

  • 自然言語の意味理解に向けた名詞や述語間の関係解析

    15th ICT innovation, Kyoto UniversityFebruary 2021
    Gave a poster presentation on my research.
    [website][poster]

Honors

Informatics, AI, and Data Science Fellowship for Doctoral Talent

April 2021 - March 2024
[website]

2nd place in 16th Young Researcher Association for NLP Studies (YANS) Symposium Hackathon

August 2022
[report][code]